Machine vision system for automatic inspection of surface defects in aluminum die casting

A camera based machine vision system for the automatic inspection of surface defects in aluminum die casting is presented. The system uses a hybrid image processing algorithm based on mathematic morphology to detect defects with different sizes and shapes. The defect inspection algorithm consists of two parts. One is a parameter learning algorithm, in which a genetic algorithm is used to extract optimal structuring element parameters, and segmentation and noise removal thresholds. The second part is a defect detection algorithm, in which the parameters obtained by a genetic algorithm are used for morphological operations. The machine vision system has been applied in an industrial setting to detect two types of casting defects: parts mix-up and any defects on the surface of castings. The system performs with a 99% or higher accuracy for both part mix-up and defect detection and is currently used in industry as part of normal production.

Automatic refinement of user requirements : a case study in software tool evaluation

This paper presents an assessment of system effectiveness in automatic requirements refinement by comparing results obtained from experts and novices with those achieved by the system. As the investigated system was a combination of a tightly inter-connected methods and a tool, the evaluation framework melded together a number of distinct methodological approaches structured into three empirical studies, which aimed at the construction of a case problem domain, calibrating the system using this defined domain elements and finally using the calibrated system to assess its effectiveness. In consequence, it was concluded that the evaluated methods and tools were effective in supporting requirements refinement.

Machine vision system for automatic inspection of surface defects in aluminium die casting

A machine vision system is presented for the automatic inspection of surface defects in aluminium die casting. The system uses a hybrid image processing algorithm based on mathematic morphology to detect defects with different sizes and shapes. The defect inspection algorithm consists of two parts. One is a parameter learning algorithm, in which a genetic algorithm is used to extract optimal structuring element parameters, and segmentation and noise removal thresholds. The second part is a defect detection algorithm, in which the parameters obtained by a genetic algorithm are used for morphological operations. The machine vision system has been applied in an industrial setting to detect two types of casting defects: parts mix-up and any defects on the surface of castings. The system performs with a 99% or higher accuracy for both part mix-up and defect detection and is currently used in industry as part of normal production.

Home, school, community and their role in the provision of music education

The Department of Education, Science and Training (DEST), is supporting under the Australian Government Quality Outcomes Programme, a National Review of School Music Education. The review, which is intended to submit its report in mid 2005, is interested in investigating the current quality of teaching and learning of music in both primary and secondary schools. It aims to provide examples of best practice of teaching and learning of music, along with a set of recommendations for the development of future approaches and directions to improve the quality of music education offerings in Australian schools. This paper puts forward some proposals for consideration that will be forwarded to the Review and aims to generate debate about future approaches to the delivery of music education in Australian primary schools.
It argues that the home, school and community all have an important part to play in the music education of children, but that at present these three entities are insufficiently connected on a number of fronts, not least being an understanding about the purpose of young people’s engagement with music. There is no doubt that interest in the arts amongst Australians generally is high. A recent Australia Council report revealed that 85 per cent of its respondents agreed the arts are and should be an important part of the education of every young Australian and that what was needed was better arts education and opportunities for all young people. However, the opportunities need not be confined to those offered by the school sector. Engagement with out-of-school music includes both music encountered in the home, which may be affected by family influence, and music provided by the diversity of community organizations, which serve a real and complimentary role to classroom learning and achieve learning outcomes that schools often do not have the resources to foster. A number of proposals for action are suggested for consideration by those involved in education as a means of progressing the discussion. It asserts that there is much valuable activity occurring within the three locales of school, home and community, but a firmer relationship could be forged across all three to ensure young people’s on-going, life-long enjoyable engagement with music.

Investigation of the value chain for creative products : a phenomenological study of the perceptions of music intermediaries

During the past decade, innovative digital technology and Internet marketplaces have created a variety of 'phenomena' of businesses, media and institutions considered to be important interaction channels in the music industry, along with an influx of Peer-to-Peer services such as Napster, and Kazaa shifting the business models of major music labels and distributors. Considering the Australian Music Association reported an annual retail turnover of approximately $300 million in 1992 and later in 1999, an increase in figures reported at $396.8 million with the inclusion of music DVD sales, the notion of value-adding to a music product emerges as a profitable venture at each length of the music industry's value chain. In spite of this, Australian studies have often overlooked the underlying perceptions, fears and ideas of those working within the value chain, especially regarding the impact of new technology on their roles. This paper identifies the perceptions of various intermediaries within the Australian Music Industry, identifying common themes and viewpoints amongst the study's participants. Consequently, the paper concluded that the perception of value in the music industry is somewhat influenced by a variety of factors, including music knowledge, communication and dependence on intermediaries to name a few. Common themes were revealed throughout the study include the perception of competitive advantage, new opportunities from new technology and the notion of defining a gimmick versus Value-Adding emerged as indicative of adding value from the study participants.

From music to silence: an exploration of music-thanatology vigils at end of life

Research in Australia into use of music-thanatology, evaluating provision of harp music in vigils with palliative care patients in a hospice. The concept of music-thanatology is outlined, and the findings of the study in alleviating suffering and creating tranquil environments are reported.

A scheme for content based retrieval of music data in MIDI format

With phenomenal increases in the generation and storage of digital audio data in several applications, there is growing need for organizing audio data in databases and providing users with fast access to desired data. This paper presents a scheme for the content-based query and retrieval of audio data stored in MIDI format. This is based on extraction of melody from the MIDI files and suitably comparing with the melody of the query. The results of retrieval using the proposed algorithm are presented.

A statistical-driven approach for automatic classification of events in AFL video highlights

Due to the repetitive and lengthy nature, automatic content-based summarization is essential to extract a more compact and interesting representation of sport video. State-of-the art approaches have confirmed that high-level semantic in sport video can be detected based on the occurrences of specific audio and visual features (also known as cinematic). However, most of them still rely heavily on manual investigation to construct the algorithms for highlight detection. Thus, the primary aim of this paper is to demonstrate how the statistics of cinematic features within play-break sequences can be used to less-subjectively construct highlight classification rules. To verify the effectiveness of our algorithms, we will present some experimental results using six AFL (Australian Football League) matches from different broadcasters. At this stage, we have successfully classified each play-break sequence into: goal, behind, mark, tackle, and non-highlight. These events are chosen since they are commonly used for broadcasted AFL highlights. The proposed algorithms have also been tested successfully with soccer video.

Towards universal and statistical-driven heuristics for automatic classification of sports video events

Researchers worldwide have been actively seeking for the most robust and powerful solutions to detect and classify key events (or highlights) in various sports domains. Most approaches have employed manual heuristics that model the typical pattern of audio-visual features within particular sport events To avoid manual observation and knowledge, machine-learning can be used as an alternative approach. To bridge the gaps between these two alternatives, an attempt is made to integrate statistics into heuristic models during highlight detection in our investigation. The models can be designed with a modest amount of domain-knowledge, making them less subjective and more robust for different sports. We have also successfully used a universal scope of detection and a standard set of features that can be applied for different sports that include soccer, basketball and Australian football. An experiment on a large dataset of sport videos, with a total of around 15 hours, has demonstrated the effectiveness and robustness of our
aIlgorithms.

Ethnomusicological study of music makers in an Australian military band

This dissertation reports on a study of music making in a band of the Australian Army Band Corps. The thesis of the dissertation is how the world views of the soldier-musicians of the Australian Army Band, Kapooka, are constructed in the context of their work in military music performance. In arguing this thesis, the author provides a brief history of military music in Australia, and - demonstrates how rank and military discipline intersect with music making in the lived experience of the soldier-musicians; - explores how the dichotomy between music making as a craft and music making as art is resolved in a setting where the employer regards music making as a trade, while the soldier-musicians strive to meet artistic goals; - demonstrates how successful music making and successful soldiering are both forms of work which depend upon effective collective action; - demonstrates that while military bands play the widest repertoire of musical styles of any Western music ensemble, the styles converge toward a homogenous, eclectic, military band performance style: and - explores how military music, which may have limited intrinsic interest, in certain ceremonial settings may link with other visual and auditory symbol systems to generate profound meaning both for the soldier-musicians themselves and for their audiences. The study examines the processes by which the world views of soldier-musicians are shaped by the institutional context in which they work, as they participate in a music tradition which has been a powerful agent in the shaping of Australian patriotic traditions. The study uses a naturalistic participant observation methodology. The author worked as an honorary guest civilian member of the band’s trombone section to collect data in the form of fieldnotes and interviews. Data analysis and interpretation was made according to the tenets of grounded theory. Evidence in the form of first hand accounts from the perspective of the researcher and from the soldier-musicians themselves is employed to generate both emic and etic understandings. An understanding of a music culture from the participant's point of view is a central concern of the study.

Automatic detection of lung nodule from computer tomography images

Lung nodule refers to lung tissue abnormalities that may become cancerous. An automated system that detects nodules of common sizes within lung images is developed. It consists of acquisition, pre-processing, background removal, nodule detection, and false positives reduction. The system can assist expert radiologists in their decision making.